Statistical Evaluation and Prediction of Financial Time Series Using Hybrid Regression Prediction Models

Abstract

Financial time series are chaotic by nature, which makes prediction difficult and complicated. This research employs the new hybrid model for the prediction of FTS which comprises Long Short-Term Memory (LSTM), Polynomial Regression (PR), and Chaos Theory. First of all, FTS is tested for the presence of chaos, in this hybrid model. Later, using Chaos Theory, the time series is modelled with the chaos existence. The model time series will be entered in LSTM for initial forecasts. The sequence of errors derived from LSTM forecasts is PR appropriate for error predictions. Error forecasts and original model forecasts are applied to produce the final hybrid model forecasts. Performance testing of the hybrid model (Chaos+LSTM+PR) is conducted using three categories namely foreign exchange, commodity price and stock-market indices. The hybrid model proposed in this study, in compliance with MSE, Dstat and Theil's U, is proved superior to the individual models like ARIMA, Prophet, LSTM and Chaos+LSTM. The execution of these various hybrid proposed methods is done mainly using Python, additionally, the authors used Gretl® and R for some methods respectively. Ultimately, the final result of this hybrid model describes with a better result than the existing prediction models and it is proved using various types of FTS like Foreign exchange rates, commodity prices, and stock market indices respectively. Hence, the result shows that the proposed hybrid models of Chaos+LSTM+PR achieved with better prediction rate than the existing models on the nine datasets executed.

Stock Market Prediction Using Generative Adversarial Networks (GANs): Hybrid Intelligent Model

“…Reference [21] discusses the difficulties of forecasting stock performance and the superiority of the suggested ensemble ARIMA-LSTM technique. In [22], a hybrid approach for predicting financial time series was presented. LSTM, Polynomial Regression (PR), and Chaos Theory make up the model.…”

Comparative Analysis of Linear Regression, Polynomial Regression, and ARIMA Model for Short-term Stock Price Forecasting

“…One of the advantages of this method over linear regression is its capability to incorporate more intricate, curved relationships that closely resemble real-world phenomena. Durairaj and BH have employed polynomial regression models for the purpose of examining and predicting various financial data, including stock prices [6]. These models have demonstrated significant predictive abilities, surpassing linear models in terms of accuracy.…”

A Review on Machine Learning for Asset Management

“…This work includes recent attention in markets to sentiment analysis or event extraction. In Durairaj and Mohan (2019), a review of deep learning hybrids for financial time-series prediction can be found. According to the authors' definition, a hybrid forecasting model combines two or more stand-alone forecasting models into a combined model in the hope to improve prediction accuracy and overcome the deficiencies of stand-alone models.…”